Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1214 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.6935. Min Range: -4.6935

Max Act: 4.6935. Min Act: -0.0000

Data Index: 638726 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 4.6935. Min Range: -4.6935

Max Act: 4.4103. Min Act: -0.0000

Data Index: 1198396 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 4.6935. Min Range: -4.6935

Max Act: 4.4433. Min Act: -0.0000

Data Index: 371365 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 4.6935. Min Range: -4.6935

Max Act: 4.3443. Min Act: -0.0000

Data Index: 662764 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 4.6935. Min Range: -4.6935

Max Act: 4.1076. Min Act: -0.0000

Data Index: 764606 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 4.6935. Min Range: -4.6935

Max Act: 3.9494. Min Act: -0.0000

Data Index: 147321 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 4.6935. Min Range: -4.6935

Max Act: 4.1192. Min Act: -0.0000

Data Index: 1045519 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 4.6935. Min Range: -4.6935

Max Act: 4.0925. Min Act: -0.0000

Data Index: 814831 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 4.6935. Min Range: -4.6935

Max Act: 4.0646. Min Act: -0.0000

Data Index: 25813 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 4.6935. Min Range: -4.6935

Max Act: 4.1475. Min Act: -0.0000

Data Index: 190080 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 4.6935. Min Range: -4.6935

Max Act: 3.9135. Min Act: -0.0000

Data Index: 1164291 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 4.6935. Min Range: -4.6935

Max Act: 3.7532. Min Act: -0.0000

Data Index: 1342973 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 4.6935. Min Range: -4.6935

Max Act: 3.8955. Min Act: -0.0000

Data Index: 850270 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 4.6935. Min Range: -4.6935

Max Act: 3.9930. Min Act: -0.0000

Data Index: 1037705 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 4.6935. Min Range: -4.6935

Max Act: 3.7983. Min Act: -0.0000

Data Index: 68656 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 4.6935. Min Range: -4.6935

Max Act: 3.7719. Min Act: -0.0000

Data Index: 931927 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 4.6935. Min Range: -4.6935

Max Act: 3.6778. Min Act: -0.0000

Data Index: 608931 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 4.6935. Min Range: -4.6935

Max Act: 3.7436. Min Act: -0.0000

Data Index: 160958 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 4.6935. Min Range: -4.6935

Max Act: 3.6427. Min Act: -0.0000

Data Index: 530772 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 4.6935. Min Range: -4.6935

Max Act: 3.8178. Min Act: -0.0000

Data Index: 581832 (C4 (Web Text))

Max Activating Token Index: 308